Learning Concise and Descriptive Attributes for Visual Recognition
This addresses the issue of interpretability and efficiency in visual recognition for researchers and practitioners, though it is incremental as it builds on existing attribute-based methods.
The paper tackles the problem of noisy and redundant LLM-generated attributes for interpretable visual recognition by proposing a learning-to-search method to find concise attribute subsets. The result is achieving performance close to using 10k attributes with only 32 attributes on the CUB dataset for 200 bird species.
Recent advances in foundation models present new opportunities for interpretable visual recognition -- one can first query Large Language Models (LLMs) to obtain a set of attributes that describe each class, then apply vision-language models to classify images via these attributes. Pioneering work shows that querying thousands of attributes can achieve performance competitive with image features. However, our further investigation on 8 datasets reveals that LLM-generated attributes in a large quantity perform almost the same as random words. This surprising finding suggests that significant noise may be present in these attributes. We hypothesize that there exist subsets of attributes that can maintain the classification performance with much smaller sizes, and propose a novel learning-to-search method to discover those concise sets of attributes. As a result, on the CUB dataset, our method achieves performance close to that of massive LLM-generated attributes (e.g., 10k attributes for CUB), yet using only 32 attributes in total to distinguish 200 bird species. Furthermore, our new paradigm demonstrates several additional benefits: higher interpretability and interactivity for humans, and the ability to summarize knowledge for a recognition task.